Mercurial > repos > estrain > seqsero2_v102
annotate deinterleave_fastq.sh @ 1:f8e2c8bc540d tip
Uploaded
| author | estrain |
|---|---|
| date | Wed, 02 Oct 2019 16:59:09 -0400 |
| parents | 18c8b4d6ab1e |
| children |
| rev | line source |
|---|---|
| estrain@0 | 1 #!/bin/bash |
| estrain@0 | 2 # Usage: deinterleave_fastq.sh < interleaved.fastq f.fastq r.fastq [compress] |
| estrain@0 | 3 # |
| estrain@0 | 4 # Deinterleaves a FASTQ file of paired reads into two FASTQ |
| estrain@0 | 5 # files specified on the command line. Optionally GZip compresses the output |
| estrain@0 | 6 # FASTQ files using pigz if the 3rd command line argument is the word "compress" |
| estrain@0 | 7 # |
| estrain@0 | 8 # Can deinterleave 100 million paired reads (200 million total |
| estrain@0 | 9 # reads; a 43Gbyte file), in memory (/dev/shm), in 4m15s (255s) |
| estrain@0 | 10 # |
| estrain@0 | 11 # Latest code: https://gist.github.com/3521724 |
| estrain@0 | 12 # Also see my interleaving script: https://gist.github.com/4544979 |
| estrain@0 | 13 # |
| estrain@0 | 14 # Inspired by Torsten Seemann's blog post: |
| estrain@0 | 15 # http://thegenomefactory.blogspot.com.au/2012/05/cool-use-of-unix-paste-with-ngs.html |
| estrain@0 | 16 |
| estrain@0 | 17 # Set up some defaults |
| estrain@0 | 18 GZIP_OUTPUT=0 |
| estrain@0 | 19 PIGZ_COMPRESSION_THREADS=10 |
| estrain@0 | 20 |
| estrain@0 | 21 # If the third argument is the word "compress" then we'll compress the output using pigz |
| estrain@0 | 22 if [[ $3 == "compress" ]]; then |
| estrain@0 | 23 GZIP_OUTPUT=1 |
| estrain@0 | 24 fi |
| estrain@0 | 25 |
| estrain@0 | 26 if [[ ${GZIP_OUTPUT} == 0 ]]; then |
| estrain@0 | 27 paste - - - - - - - - | tee >(cut -f 1-4 | tr "\t" "\n" > $1) | cut -f 5-8 | tr "\t" "\n" > $2 |
| estrain@0 | 28 else |
| estrain@0 | 29 paste - - - - - - - - | tee >(cut -f 1-4 | tr "\t" "\n" | pigz --best --processes ${PIGZ_COMPRESSION_THREADS} > $1) | cut -f 5-8 | tr "\t" "\n" | pigz --best --processes ${PIGZ_COMPRESSION_THREADS} > $2 |
| estrain@0 | 30 fi |